> For the complete documentation index, see [llms.txt](https://docs.ovaledge.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ovaledge.com/administration/audit-trails/ai.md).

# AI

Various actions that have taken place using the AI integrated with OvalEdge to generate or modify a business or technical or detailed description and user interactions with AskEdgi are audited here. 

### Description Generation

The Description Generation tab captures details of business or technical or detailed descriptions created, updated, or deleted in the Data Catalog and Business Glossary modules using AI. It includes:

**AI Engine:** Name of the corresponding AI Engine that is used

**AI Model:** Model of the corresponding AI Engine

**Object Type:** The type of the Data Object, on which the AI prompt was run

**Object Name:** The name of the Data Object, on which the AI prompt was run

**Field:** Was AI used to create or modify a Business or Technical or Detailed Description

**Prompt to AI:** The prompt requested by the end-user

**Instructions:** Special instructions given from the application end to generate a better description

**AI Response:** The response generated by the AI

**Error Message:** If any Error is thrown, that is captured and shown

**Total Tokens:** Total number of tokens that were consumed for this action

**Created By:** The user who has made this action

**Created On:** The timestamp of the action

Sample screenshot featuring Audit Trails > AI > Description Generation information.

<figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXfG7W0hNXWo0HE3qXUQy2UE_UQOcmNIUVtE0-AjMjo4pQDkGN71wZCy07yIrr9402aMX7vI0ywgR8ioal1ZH6RgH45vWPTpEW5qNHl8RKtBEjaW2axyu-EUsFopi0N5tYz6bd7mIQ?key=3Q1-FAinoXRbCvW1iecCwIKR" alt=""><figcaption></figcaption></figure>

### AskEdgi

The AskEdgi tab records details of user interactions with the AI, capturing the AI Prompt (The prompt provided by the user to AskEdgi) and AI Response (The response generated by AskEdgi is based on the user’s prompt). It includes:

* **AI Engine:** Name of the corresponding AI Engine that is used
* **AI Model:** Model of the corresponding AI Engine
* **User Name:** Name of the user who was using AskEdgi
* **Prompt to AI:** The prompt provided by the user to AskEdgi
* **Response from AI:** The response generated by AskEdgi is based on the user’s prompt
* **Error Message:** If any Error is thrown, that is captured and shown
* **AI Input Tokens:** Total number of tokens that were consumed for this action
* **AI Output Tokens:** Total number of tokens that were delivered for this action
* **Created Date:** The timestamp of the action

Sample screenshot featuring Audit Trails > AI > AskEdgi information.

<figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXdxFxrIU-FahTnx9zblPY8sXdh1BhZllQFTIozKGB07O7bQXUneKFFI12V-xle7d4t2SIJyGG4N4TfPkgUvjSERVhp_jpvd6o3c_7ERPxW6RvZNVTojt-30MNB3DwKFv3epIMwM?key=3Q1-FAinoXRbCvW1iecCwIKR" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.ovaledge.com/administration/audit-trails/ai.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.